Initial commit: hardened DeerFlow factory

Vendored deer-flow upstream (bytedance/deer-flow) plus prompt-injection
hardening:

- New deerflow.security package: content_delimiter, html_cleaner,
  sanitizer (8 layers — invisible chars, control chars, symbols, NFC,
  PUA, tag chars, horizontal whitespace collapse with newline/tab
  preservation, length cap)
- New deerflow.community.searx package: web_search, web_fetch,
  image_search backed by a private SearX instance, every external
  string sanitized and wrapped in <<<EXTERNAL_UNTRUSTED_CONTENT>>>
  delimiters
- All native community web providers (ddg_search, tavily, exa,
  firecrawl, jina_ai, infoquest, image_search) replaced with hard-fail
  stubs that raise NativeWebToolDisabledError at import time, so a
  misconfigured tool.use path fails loud rather than silently falling
  back to unsanitized output
- Native client back-doors (jina_client.py, infoquest_client.py)
  stubbed too
- Native-tool tests quarantined under tests/_disabled_native/
  (collect_ignore_glob via local conftest.py)
- Sanitizer Layer 7 fix: only collapse horizontal whitespace, preserve
  newlines and tabs so list/table structure survives
- Hardened runtime config.yaml references only the searx-backed tools
- Factory overlay (backend/) kept in sync with deer-flow tree as a
  reference / source

See HARDENING.md for the full audit trail and verification steps.
This commit is contained in:
2026-04-12 14:23:57 +02:00
commit 6de0bf9f5b
889 changed files with 173052 additions and 0 deletions

78
.gitignore vendored Normal file
View File

@@ -0,0 +1,78 @@
# ============================================================================
# Secrets — NEVER commit
# ============================================================================
.env
.env.local
.env.*.local
secrets/
*.pem
*.key
!**/test*.pem
!**/test*.key
# ============================================================================
# Python
# ============================================================================
__pycache__/
*.pyc
*.pyo
*.pyd
.venv/
venv/
.pytest_cache/
.mypy_cache/
.ruff_cache/
*.egg-info/
.coverage
htmlcov/
# ============================================================================
# Node / pnpm / npm
# ============================================================================
node_modules/
.pnpm-store/
.next/
dist/
build/
*.log
# ============================================================================
# Editor / OS
# ============================================================================
.vscode/
.idea/
.DS_Store
Thumbs.db
*.swp
*.swo
*~
# ============================================================================
# DeerFlow runtime
# ============================================================================
deer-flow/.deer-flow/
deer-flow/backend/.deer-flow/
deer-flow/backend/uploads/
deer-flow/backend/checkpoints/
deer-flow/backend/threads/
deer-flow/docker/.cache/
deer-flow/.omc/
# Local DeerFlow config (overlay) — only the example/template lives in git
deer-flow/config.yaml
deer-flow/backend/config.yaml
deer-flow/mcp_config.json
deer-flow/extensions_config.json
# Quarantined upstream tests for disabled native providers
# (kept on disk but excluded from collection — see conftest.py inside)
# We DO want them in git so the disable trail is visible.
!deer-flow/backend/tests/_disabled_native/
# ============================================================================
# Backups / scratch
# ============================================================================
*.bak
*.backup
*.tmp
.scratch/